Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5444 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2436. Min Range: -7.2436
Max Act: 7.2124. Min Act: -0.1700
Data Index: 685091 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2436. Min Range: -7.2436
Max Act: 7.2436. Min Act: -0.1700
Data Index: 8779939 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2436. Min Range: -7.2436
Max Act: 7.0249. Min Act: -0.1700
Data Index: 4101680 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.9936. Min Act: -0.1700
Data Index: 2565603 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.9624. Min Act: -0.1700
Data Index: 7733019 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.9624. Min Act: -0.1700
Data Index: 5541602 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.8999. Min Act: -0.1700
Data Index: 2868586 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.8686. Min Act: -0.1700
Data Index: 3176857 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.7749. Min Act: -0.1700
Data Index: 2069088 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.7749. Min Act: -0.1700
Data Index: 5667017 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.7436. Min Act: -0.1700
Data Index: 3896308 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.7124. Min Act: -0.1700
Data Index: 8439574 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.7124. Min Act: -0.1700
Data Index: 6637502 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.7124. Min Act: -0.1700
Data Index: 3135689 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.6811. Min Act: -0.1700
Data Index: 3104917 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.6811. Min Act: -0.1700
Data Index: 2695153 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.6499. Min Act: -0.1700
Data Index: 4947542 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.6499. Min Act: -0.1700
Data Index: 2286403 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.6811. Min Act: -0.1700
Data Index: 6811878 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2436. Min Range: -7.2436
Max Act: 6.5874. Min Act: -0.1700
Data Index: 5333463 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19